GPT-5.2 vs MiniMax M2.5
GPT-5.2 leads MiniMax M2.5 on coding, 55.9 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 11.7x less per output token ($1.20 vs $14.00 per million). Updated October 22, 2026; 66 benchmarks have a result for both.
GPT-5.2 or MiniMax M2.5: which to pick
Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 37.2 for MiniMax M2.5.
Pick MiniMax M2.5 for output tokens 11.7x cheaper ($1.20 vs $14.00 per million) and a lower cost per solved task ($0.62 against $1.91).
- Shared results
- 66
- GPT-5.2 only
- 48
- MiniMax M2.5 only
- 2
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.2
GPT-5.2 scores 55.9 against 37.2.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 22.8.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 82.1%.
Same board, both measured
Math
AIME
GPT-5.2
GPT-5.2 leads, 96.9% against 88.8%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.2
GPT-5.2 leads, 86.2% against 80.1%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M2.5
MiniMax M2.5 leads, 1222 against 1195.
Same board, both measured
Long documents
Listed context window
GPT-5.2
GPT-5.2 takes 400K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
GPT-5.2 $0.0088, MiniMax M2.5 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M2.5
GPT-5.2 $1.91, MiniMax M2.5 $0.62.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, MiniMax M2.5 37.2 from 3 benchmarks.
- Widest category
- Reasoning, 16.6 points apart on average over 9 shared benchmarks.
- Widest single gap
- ARC-AGI-2: GPT-5.2 52.9% against MiniMax M2.5 4.9%, 48.1 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against MiniMax M2.5 $1.20 per million output tokens, 11.7x apart.
- Context window
- GPT-5.2 takes 400K tokens, MiniMax M2.5 205K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5.2 | Bars | MiniMax M2.5 | Ties |
|---|---|---|---|---|
| Coding | 10 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 9 | 0 | ||
| Math | 4 | 0 | ||
| Knowledge | 10 | 0 | ||
| Web design | 3 | 4 | ||
| General | 20 | 0 | ||
| All shared boards | 59 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index102
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | 75.8% | MiniMax M2.5 |
| SWE-bench Multilingual | 66.7% | 68.3% | MiniMax M2.5 |
| LMArena WebDev | 1417 | 1386 | GPT-5.2 |
| LiveCodeBench (Vals AI) | 85.4% | 79.2% | GPT-5.2 |
| SWE-bench Verified (Vals AI) | 75.8% | 74.2% | GPT-5.2 |
| Vibe Code Bench (Vals AI) | 53.5% | 14.8% | GPT-5.2 |
| LiveCodeBench (Artificial Analysis run) | 89.4% | Not measured | Only GPT-5.2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 34.8% | GPT-5.2 |
| Terminal-Bench | 64.9% | 42.7% | GPT-5.2 |
| GSO-Bench | 27.5% | Not measured | Only GPT-5.2 measured |
| WeirdML | 72.2% | Not measured | Only GPT-5.2 measured |
| ALE-Bench | 1293.5 | 618.2 | GPT-5.2 |
| LMArena Text: coding | 1442 | 1380 | GPT-5.2 |
| LMArena Text: software and IT | 1434 | 1383 | GPT-5.2 |
| LMArena WebDev: React | Not measured | 1374 | Only MiniMax M2.5 measured |
| LMArena WebDev: HTML | 1427 | 1414 | GPT-5.2 |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 22.8 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | 146.6 | GPT-5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1086 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building full-stack apps | 1043 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building mobile apps | 1093 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Android apps | 1060 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2 measured |
| τ²-Bench Telecom | 84.8% | 95.3% | MiniMax M2.5 |
| METR time horizons | 75.3% | Not measured | Only GPT-5.2 measured |
| Remote Labor Index | 2.5% | Not measured | Only GPT-5.2 measured |
| GDPval | 49.7% | Not measured | Only GPT-5.2 measured |
| DeepResearch Bench | 41.1% | Not measured | Only GPT-5.2 measured |
| Vending-Bench 2 | $3,591 | -$23 | GPT-5.2 |
| Berkeley Function Calling Leaderboard (BFCL) | 55.9% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | 82.1% | GPT-5.2 |
| MMMU Pro (Vals AI) | 86.7% | Not measured | Only GPT-5.2 measured |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 84.8% | GPT-5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 20.5% | GPT-5.2 |
| GPQA Diamond (Epoch AI run) | 91.4% | Not measured | Only GPT-5.2 measured |
| ARC-AGI | 86.2% | 63.7% | GPT-5.2 |
| ARC-AGI-2 | 52.9% | 4.9% | GPT-5.2 |
| SimpleBench | 45.8% | Not measured | Only GPT-5.2 measured |
| Chess puzzles | 48.0% | Not measured | Only GPT-5.2 measured |
| Mystery game puzzles | 23.0% | Not measured | Only GPT-5.2 measured |
| EBR-bench | 23.0% | Not measured | Only GPT-5.2 measured |
| VPCT | 84.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts | 1428 | 1372 | GPT-5.2 |
| LMArena Text: expert | 1445 | 1378 | GPT-5.2 |
| LMArena Text: hard prompts in English | 1431 | 1384 | GPT-5.2 |
| LMArena Vision: diagrams | 1265 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: homework | 1276 | Not measured | Only GPT-5.2 measured |
| Kagi LLM Benchmark | 73.3% | 55.2% | GPT-5.2 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| AIME | 96.9% | 88.8% | GPT-5.2 |
| MGSM (Vals AI) | 94.0% | Not measured | Only GPT-5.2 measured |
| AA Math Index | 99.0 | Not measured | Only GPT-5.2 measured |
| AIME 2025 (Artificial Analysis run) | 99.0% | Not measured | Only GPT-5.2 measured |
| OTIS Mock AIME | 96.1% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tiers 1 to 3 | 67.4% | Not measured | Only GPT-5.2 measured |
| FrontierMath, tier 4 | 31.7% | Not measured | Only GPT-5.2 measured |
| ProofBench | 15.0% | 4.0% | GPT-5.2 |
| LMArena Text: math | 1440 | 1378 | GPT-5.2 |
| LMArena Text: mathematical work | 1442 | 1378 | GPT-5.2 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 80.1% | GPT-5.2 |
| LegalBench (Vals AI) | 82.8% | 80.0% | GPT-5.2 |
| CaseLaw (Vals AI) | 66.0% | 53.5% | GPT-5.2 |
| CorpFin (Vals AI) | 65.9% | 59.6% | GPT-5.2 |
| TaxEval (Vals AI) | 75.8% | 68.2% | GPT-5.2 |
| MortgageTax (Vals AI) | 67.1% | Not measured | Only GPT-5.2 measured |
| MedQA (Vals AI) | 94.1% | 92.5% | GPT-5.2 |
| MedCode (Vals AI) | 49.8% | Not measured | Only GPT-5.2 measured |
| MMLU Pro (Artificial Analysis run) | 87.4% | Not measured | Only GPT-5.2 measured |
| SimpleQA Verified | 37.1% | Not measured | Only GPT-5.2 measured |
| LMArena Text: science | 1425 | 1369 | GPT-5.2 |
| LMArena Text: medicine and healthcare | 1425 | 1357 | GPT-5.2 |
| LMArena Text: legal and government | 1427 | 1366 | GPT-5.2 |
| LMArena Text: business and finance | 1414 | 1356 | GPT-5.2 |
| FACTS Benchmark Suite | 48.5% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index34
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | 1222 | MiniMax M2.5 |
| Design Arena: UI components | 1188 | 1170 | GPT-5.2 |
| Design Arena: game dev | 1195 | 1176 | GPT-5.2 |
| Design Arena: data viz | 1202 | 1172 | GPT-5.2 |
| Design Arena: 3D | 1079 | 1170 | MiniMax M2.5 |
| Design Arena: all code categories | 1170 | 1207 | MiniMax M2.5 |
| Design Arena: SVG | 1139 | 1150 | MiniMax M2.5 |
| Design Arena: ASCII art | 1152 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | Not measured | Only GPT-5.2 measured |
| MedScribe (Vals AI) | 84.4% | Not measured | Only GPT-5.2 measured |
| IFBench | 75.4% | 71.6% | GPT-5.2 |
| Long context reasoning (AA-LCR) | 82.7% | 73.3% | GPT-5.2 |
| DTBench | 90.9% | Not measured | Only GPT-5.2 measured |
| LMCA | 43.9% | Not measured | Only GPT-5.2 measured |
| CL-bench | 18.2% | 11.4% | GPT-5.2 |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| CL-bench Life | Not measured | 6.3% | Only MiniMax M2.5 measured |
| LMArena Text | 1416 | 1359 | GPT-5.2 |
| LMArena Text: instruction following | 1409 | 1353 | GPT-5.2 |
| LMArena Text: creative writing | 1376 | 1331 | GPT-5.2 |
| LMArena Vision | 1246 | Not measured | Only GPT-5.2 measured |
| LMArena Text: English | 1422 | 1380 | GPT-5.2 |
| LMArena Text: non-English | 1405 | 1338 | GPT-5.2 |
| LMArena Text: Chinese | 1447 | 1393 | GPT-5.2 |
| LMArena Text: German | 1444 | 1361 | GPT-5.2 |
| LMArena Text: Japanese | 1420 | 1171 | GPT-5.2 |
| LMArena Text: Korean | 1374 | 1233 | GPT-5.2 |
| LMArena Text: French | 1454 | 1363 | GPT-5.2 |
| LMArena Text: Spanish | 1413 | 1353 | GPT-5.2 |
| LMArena Text: Russian | 1415 | 1359 | GPT-5.2 |
| LMArena Text: Polish | 1426 | 1334 | GPT-5.2 |
| LMArena Text: multi-turn | 1419 | 1364 | GPT-5.2 |
| LMArena Text: longer queries | 1413 | 1366 | GPT-5.2 |
| LMArena Text: writing and language | 1392 | 1345 | GPT-5.2 |
| LMArena Text: entertainment and media | 1378 | 1329 | GPT-5.2 |
| LMArena Vision: English | 1243 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: Chinese | 1305 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: reading text | 1257 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: humor | 1227 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: captioning | 1267 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: recognizing things | 1232 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: creative writing | 1225 | Not measured | Only GPT-5.2 measured |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | MiniMax M2.5 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiniMax M2.5 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.5 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.2 | MiniMax M2.5 |
|---|---|---|
| Maker | OpenAI | MiniMax |
| Weights | No public weights listed | Open weights |
| Released | December 10, 2025 | February 12, 2026 |
| Context window | 400K | 205K |
| Input $/Mtok | $1.75 | $0.30 |
| Output $/Mtok | $14.00 | $1.20 |
| Coding index | 55.9 | 37.2 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $1.91 | $0.62 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than MiniMax M2.5 for coding?
Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 11.7x cheaper ($1.20 vs $14.00 per million) and a lower cost per solved task ($0.62 against $1.91).
Which is cheaper, GPT-5.2 or MiniMax M2.5?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Per solved SWE-bench Verified task, GPT-5.2 costs $1.91 and MiniMax M2.5 $0.62.
Which has the bigger context window, GPT-5.2 or MiniMax M2.5?
GPT-5.2, with 400K tokens against 205K.
How many benchmarks is the GPT-5.2 vs MiniMax M2.5 comparison based on?
66 benchmarks have a result for both models as of October 22, 2026. GPT-5.2's coding index rests on 3 independent benchmarks and MiniMax M2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.